2020/06/19 by Jihwan Bang, Bang, Jihwan, Heesu Kim +6
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning and Algorithms #Natural Language Processing Techniques #Speech Recognition and Synthesis #cs.LG #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2006.11021
8 pages, 4 figures, 2 tables
openalex publication_date 2020/06/19 · arxiv created 2020/11/05 · arxiv updated 2020/11/06 · openalex created_date 2020/11/09 · openalex updated_date 2026/07/28
The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training pipeline boosting the conventional active learning approach targeting label-efficient learning to resolve the mentioned problem. Existing active learning methods only focus on selecting a set of informative samples under a labeling budget. One step further, we suggest that the training efficiency can be further improved by utilizing the unlabeled samples, exceeding the labeling budget, by introducing sophisticatedly configured unsupervised loss complementing supervised loss effectively. We propose new unsupervised loss based on consistency regularization, and we configure appropriate augmentation techniques for utterances to adopt consistency regularization in the automatic speech recognition task. From the qualitative and quantitative experiments on the real-world dataset and under real-usage scenarios, we show that the proposed training pipeline can boost the efficacy of active learning approaches, thus successfully reducing a sustainable amount of human labeling cost.